You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

31 lines
1.2 KiB

import requests
from bs4 import BeautifulSoup
import urllib.request
url='https://www.gushiwen.cn/user/login.aspx'
headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/133.0.0.0 Safari/537.36'}
response = requests.get(url,headers=headers)
content=response.text
soup=BeautifulSoup(content,'lxml')
code=soup.select('#imgCode')[0].attrs.get('src')
code_url='https://www.gushiwen.cn'+code
session=requests.Session()#建立会话
response_code=session.get(code_url)
content_code=response_code.content
with open('code.jpg','wb') as f:
f.write(content_code)
code_num=input("验证码:")
data={
'__VIEWSTATE': '/wEPDwUKLTU5OTg0MDIwNw8WAh4TVmFsaWRhdGVSZXF1ZXN0TW9kZQIBZGQGi0FCmPHMP+KelvQVsoBoqE2Axg==',
'__VIEWSTATEGENERATOR': 'C93BE1AE',
'from': '',
'email': '3160722440@qq.com',#你的账号
'pwd': 'hwh3160722440',#你的密码
'code': code_num,#code.jpg获取的验证码
'denglu': '登录'
}
response_post=session.post(url,headers=headers,data=data)
my_url='https://www.gushiwen.cn/user/collect.aspx'
my_response=session.get(my_url,headers=headers)
my_content=my_response.text
with open('古诗文网.html','w',encoding='utf-8') as f:
f.write(my_content)